Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #321115

Title: Detection of lettuce discoloration using hyperspectral reflectance imaging

Author
item MO, CHANGYEUN - Rural Development Administration - Korea
item KIM, GIYOUNG - Rural Development Administration - Korea
item LIM, JONGGUK - Rural Development Administration - Korea
item Kim, Moon
item CHO, HYUNJEONG - Chungnam National University
item CHO, BYOUNG-KWAN - Rural Development Administration - Korea

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/17/2015
Publication Date: 11/20/2015
Citation: Mo, C., Kim, G., Lim, J., Kim, M.S., Cho, H., Cho, B. 2015. Detection of lettuce discoloration using hyperspectral reflectance imaging. Sensors. 15(12):29511-29534.

Interpretive Summary: There are increasing consumer demands for high quality fresh produce. Hyperspectral imaging technology can be used to evaluate produce quality. In this study, hyperspectral imaging was evaluated as a means for rapidly determining discoloration of lettuce leaves. Multispectral imaging algorithms, using ratio and subtraction functions, were able to detect discolorations on both surfaces of lettuce surfaces with 100 % accuracy. This study shows that rapid reflectance imaging techniques can potentially be used as an online imaging method to discriminate between discolored and sound fresh-cut lettuce. This provides insightful information to agricultural engineers who are developing non-destructive fresh produce quality and safety optical inspection technologies.

Technical Abstract: Rapid visible/near-infrared (VNIR) hyperspectral imaging methods, employing both a single waveband algorithm and multi-spectral algorithms, were developed in order to classify the discoloration of lettuce. Reflectance spectra for sound and discolored lettuce surfaces were extracted from hyperspectral absorbance images obtained in the 400–1000 nm wavelength range. The optimal wavebands for discriminating between discolored and sound lettuce surfaces were determined using one-way analysis of variance. Multispectral imaging algorithms developed using ratio and subtraction functions resulted in enhanced classification accuracy of 100 % for discolored and sound areas on both adaxial and abaxial lettuce surfaces. Ratio imaging (RI) and subtraction imaging (SI) algorithms at wavelengths of 552/701 nm and 557-701 nm, respectively, exhibited better classification performances compared to results obtained for all possible two-waveband combinations. These results suggest that hyperspectral reflectance imaging techniques can potentially be used to discriminate between discolored and sound fresh-cut lettuce.